%load_ext pretty_jupyter

# import packages
import pandas as pd
from SPARQLWrapper import SPARQLWrapper, JSON
import json

sparqlep = "http://graph.oceaninfohub.org/blazegraph/namespace/oih/sparql"

from minio import Minio

def publicurls(client, bucket, prefix):
    urls = []
    objects = client.list_objects(bucket, prefix=prefix, recursive=True)
    for obj in objects:
        result = client.stat_object(bucket, obj.object_name)

        if result.size > 0:  #  how to tell if an objet   obj.is_public  ?????
            url = client.presigned_get_object(bucket, obj.object_name)
            # print(f"Public URL for object: {url}")
            urls.append(url)

    return urls

client = Minio("ossapi.oceaninfohub.org:80",  secure=False) # Create client with anonymous access.

def get_sparql_dataframe(service, query):
    """
    Helper function to convert SPARQL results into a Pandas data frame.
    """
    sparql = SPARQLWrapper(service)
    sparql.setQuery(query)
    sparql.setReturnFormat(JSON)
    result = sparql.query()

    processed_results = json.load(result.response)
    cols = processed_results['head']['vars']

    out = []
    for row in processed_results['results']['bindings']:
        item = []
        for c in cols:
            item.append(row.get(c, {}).get('value'))
        out.append(item)

    return pd.DataFrame(out, columns=cols)

# we create a simple dataframe for demonstration purposes
urls = publicurls(client, "public", "graph")

rq_pcount = """SELECT ?p (COUNT(?p) as ?pCount)
WHERE
{
  ?s ?p ?o .
}
GROUP BY ?p
"""
dfc = get_sparql_dataframe(sparqlep, rq_pcount)
dfc['pCount'] = dfc["pCount"].astype(int) # convert count to int
# dfc.set_index('p', inplace=True)
dfc_sorted = dfc.sort_values('pCount', ascending=False)